© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21787
    Prev
    Next
    INDEX
    Explanations

    somatic, down-regulation, collective voice, blogs, hybrid vehicle, inequities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     B
    -0.05
     inquiry
    -0.05
    ÙĩÙIJ
    -0.05
     пов
    -0.05
    æĮ¥
    -0.05
     prepared
    -0.05
    éĩį大影åĵį
    -0.05
    (
    -0.05
    çªĥ
    -0.05
     combined
    -0.05
    POSITIVE LOGITS
    åħ·æľīå¾Īé«ĺçļĦ
    0.06
    orse
    0.06
    ieke
    0.06
    unate
    0.06
    iris
    0.06
    urale
    0.06
    uali
    0.06
    etsk
    0.06
    ئات
    0.06
     Avalanche
    0.06
    Activations Density 0.138%

    No Known Activations